gpu4.pics
data via LocalScore
NVIDIA RTX 4090
24 GB VRAM NVIDIA 450 W TDP
running Qwen2.5 14B Instruct· Q4_K_M· 14.8B
49.1
tokens / sec
766 · Strong #9 of 373
Generation
49.1tok/s
higher is better
Prompt / prefill
3,506tok/s
higher is better
Time to first token
396 ms
lower is better
Composite score
766
Model size
14.8B
Runtime
—
All benchmarks on this rig
| Model | Quant | Gen | Prompt | TTFT | Power | Perf/W | $/Mtok | Score |
|---|---|---|---|---|---|---|---|---|
| Qwen2.5 14B Instruct14.8B | Q4_K_M | 49.1 | 3,506 | 396 ms | — | — | — | 766 |